© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66518
    Prev
    Next
    INDEX
    Explanations

    variable names and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.17
    ’
    -1.81
     mereka
    -1.67
    <bos>
    -1.66
     still
    -1.47
     就是
    -1.43
     fotografias
    -1.36
     
    -1.32
     so
    -1.31
    али
    -1.25
    POSITIVE LOGITS
    .
    1.63
     entwickelte
    1.59
    🥿
    1.59
     sufrir
    1.55
     viviendas
    1.55
     zusätz
    1.54
    ntesis
    1.52
    無料で
    1.48
    푐
    1.48
    ?
    1.47
    Activations Density 0.006%

    No Known Activations